The objective of this thesis is to implement a client-server system with a web-based user interface for content-based searching in an image-based database. The database will keep standard images or key-frame images extracted from video data. The main system functionality will support the specification of a text query in a natural language description and search for database images that are relevant to the specified query. The technology of the system will be based on successful text-to-image retrieval models and efficient image feature indexing mechanisms. The textual part will contain the description of state-of-the-art cross-modal retrieval technologies along with the design and implementation of the proposed system.