The Content-based image retrieval (CBIR) systems and their application in different areas of development, are current research topics, however many of this systems are likely to fail due to use global features which cannot sufficiently capture the important properties of individual objects [1] because generally a typical query image includes relevant objects (e.g., Eiffel Tower), but also irrelevant image areas (including background). Then recently, many research has focused on region-based techniques that allow the user to specify a particular region of an image and the system will return images with similar regions to the query. For that reason this paper proposes a method of retrieval image based on irregular regions of interest where the user can to select one region. Preliminary experimental results show that the proposed method provides better retrieving result than retrieval using some of the existing methods.