The adoption of an appropriate approximate similarity search method is an essential prerequisite for developing a fast and efficient CBIR system, especially when dealing with large amount of data. In this study we implement a web image search engine on top of a Locality Sensitive Hashing (LSH) Index to allow fast similarity search on deep features. Specifically, we exploit transfer learning for deep features extraction from images. Firstly, we adopt InceptionV3 pretrained on ImageNet as features extractor, secondly, we try out several CNNs built on top of InceptionV3 as convolutional base fine-tuned on our dataset. In both of the previous cases we index the features extracted within our LSH index implementation so as to compare the retrieval performances with and without fine-tuning. In our approach we try out two different LSH implementations: the first one working with real number feature vectors and the second one with the binary transposed version of those vectors. Interestingly, we obtain the best performances when using the binary LSH, reaching almost the same result, in terms of mean average precision, obtained by performing sequential scan of the features, thus avoiding the bias introduced by the LSH index. Lastly, we carry out a performance analysis class by class in terms of recall against mAP highlighting, as expected, a strong positive correlation between the two.