The evolution in the digital technology from the last few decades and different multimedia sources like Broadcast news, Movies, Videos, images, etc. have increased the size volume of the digital media daily. Due to this explosive growth in the digital media volume, it's strongly urged for the system that efficiently and effectively compiles the user demand and retrieving the relevant images. In this paper, the user query will be expanded through an open-source knowledge base WordNet and ConceptNet for retrieves the images on the base of different synonyms and concepts. This technique covers the word mismatch and word sense disambiguation (WSD) problem. Propose method effectively applied on the open benchmark image dataset LabelMe. The experimental results show that of the propose techniques have improved the retrieval performance over the traditional ones and get the accuracy up to 94 for single word and 83 for sentence word queries. © 2011 Springer-Verlag.