With the tremendous revolutions in the digital technology and ease of use in the results large volumes of images generated. In such types gigantic image corpus it is hardly to find the relevant images. Different researchers have defined techniques to retrieve images with high accuracy but still not cope in the semantic gap and lexical ambiguity. This paper focused on short query expansion i.e. expands user query with ConceptNet and WordNet knowledge bases. It retrieved the images, even if they are labeled with different words. The experiments showed the performance of this proposed algorithm, that retrieves images effectively and efficiently from LabelMe dataset. © 2012 IEEE.