In recent Face image Retrieval in the Large scale Systems is to be very difficult. We have to detect the human Face by some Preprocessing techniques. For Efficiency in large scale system, we have to use two orthogonal methods called Feature Extracted sparse coding and Classification-based inverted indexing in both offline and online stages. We have to effective Face retrieval with vital essential factors in Different properties in Faces. Now a days the popularity of social networks like face book, twitter are mostly used by the people. Many of them use human face images to their profile. And also we can maintain large scale database for the image storage. To avoid the large database use two algorithms like attribute enhanced sparse code words and attribute embedded inverted indexing and used in offline and online storage respectively. In large image database have problem regarding the image retrieval .By using this algorithm we can efficiently retrieve the images from the large image database. It will give the 80% perfect matched images. Face image retrieval from the large scale databases is the challenging problem and is beneficial to many real world applications. In this paper I propose to develop a method where I exploit special properties of faces like local features based on hamming distance to encode discriminative global feature for each face in order to retrieve the required image from large scale database.