Journal of Digital Information Management Sakila A, Vijayarani S 16 3 2018 https://doi.org/10.6025/jdim/2018/16/3/136-151 http://dline.info/fpaper/jdim/v16i3/jdimv16i3_4.pdf The main objective of this research work is to find the keywords in the captured/scanned print document images in the image database. Document images are becoming more popular in today's world and these are used in paperless offices and digital libraries. Information retrieval from the document images is a very challenging task. Hence, there is a need for developing searching strategies to find the required information from these document images as per user's needs, becomes very essential in nowadays. Traditionally Optical Character Recognition (OCR) tools are used for information retrieval from the document images, but it's not an efficient method. Word spotting is an inventive method for searching the document images and to retrieve relevant information without any conversion. In this work an algorithm Enhanced Dynamic Time Warping was proposed to for finding keywords from document images, it is based on word spotting technique. Different matching algorithms are made available for word spotting. Popular algorithms are Normalization Cross Correlation (NCC) and Dynamic Time Warping (DTW). In this work, we have compared the performance of these two existing algorithms with the proposed algorithm named as Enhanced Dynamic Time Warping algorithm (EDTW). Different image formats and different sizes of images are used for experimentation. From the results it is observed that the proposed algorithm has produced good results than an existing one.