I-SEARCH aims to create a novel unified framework for multimedia and multimodal content indexing, sharing, search and retrieval. I-SEARCH will be the first search engine able to handle specific types of multimedia (text, 2D image, sketch, video, 3D objects, audio and combination of the above) and multimodal content (gestures, face expressions, eye movements) along with real world information (GPS, temperature, time, weather sensors, RFID objects,), which can be used as queries and retrieve any available relevant content of any of the aforementioned types and from any end-user access device. Towards this aim, I-SEARCH proposes the research and development of an innovative Rich Unified Content Description (RUCoD). RUCoD will consist of a multi-layered structure, which will integrate descriptors of all of the above types of content, real-world information, even non-verbal yet implicit, emotional cues and social descriptors, in order to better express what the user wants to retrieve. Another objective of I-SEARCH is the development of intelligent content interaction mechanisms, including personal, social-based and recommendation-based relevance feedback and novel interoperable multimodal interfaces. This will result in a highly user-centric search engine, able to deliver to the end-users only the content of interest, satisfying their information needs and preferences, which is expected to dramatically improve end-user experience and offer new market opportunities. Furthermore, I-SEARCH introduces the use of advanced visual analytic technologies for search results presentation in order to facilitate their fast and easy interpretation and also to support optimal results presentation under various contexts (i.e. user profile, end-user terminal, available network bandwidth, interaction modality preference, etc.). Finally, the search engine will be dynamically adapted to end-user's device, which will vary from a simple mobile phone to a high-performance PC.