This shell script file for finding the pdf files which probably include no OCRed text.

findNoTextPdf.sh

#!/bin/bash
if [ $# -ne 1 ]; then
  echo "Usage: findNoTextPdf.sh path"
  exit 1
fi

find $1 -type f -name "*.pdf" | while read myfile
do
  pdftotext -l 1 "$myfile" tmp 
  status=`hexdump -ve '1/1 "%.2x"' tmp | head -c 2`
  if [ $status == "0c" ]; then
    echo $myfile
  fi  
done
rm tmp